Instructions to use carloshuang1224/MiMo-V2.5-ASR-MLX-BF16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use carloshuang1224/MiMo-V2.5-ASR-MLX-BF16 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir MiMo-V2.5-ASR-MLX-BF16 carloshuang1224/MiMo-V2.5-ASR-MLX-BF16
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
MiMo-V2.5-ASR MLX BF16
This repository contains the bfloat16 ASR checkpoint package generated from the
local MiMo-V2.5-ASR safetensors. It is the current default precision for the
mimo_mlx Apple Silicon inference code.
Files
model-00001-of-00007.safetensors...model-00007-of-00007.safetensorsmodel.safetensors.index.json- Qwen tokenizer/config sidecar files
Load
from mimo_mlx import load_asr
asr = load_asr("bf16")
text = asr.transcribe("audio.wav", language="zh")
The audio tokenizer is required separately. Use the official
XiaomiMiMo/MiMo-Audio-Tokenizer files or the local directory expected by the
project.
Validation
On the local VoiceInk-History seeded spread check, bf16 preserved the validated float32 behavior.
Source
Base model: https://huggingface.co/XiaomiMiMo/MiMo-V2.5-ASR
- Downloads last month
- 299
Model size
8B params
Tensor type
BF16
·
Hardware compatibility
Log In to add your hardware
Quantized
Model tree for carloshuang1224/MiMo-V2.5-ASR-MLX-BF16
Base model
XiaomiMiMo/MiMo-V2.5-ASR